Differences

This shows you the differences between two versions of the page.

--- aira:start [2026/10/12 18:00] – [Artificial Intelligence in Research and Applications Seminar (AIRA)] gjn
+++ aira:start [2026/10/15 00:13] (current) – [2026-06-18] mzk
@@ Line 21: / Line 21: @@
 ===== Schedule Autumn 2027 =====
+* **[PHD TRACK] 2026.10.30**: Enrique Valero,  PhD Candidate @ Technical University of Madrid, [[#section20261015|Group counterfactual explanations: State-of-the-art and future research.]]
+  * Meeting link:[[https://teams.microsoft.com/meet/3403291934979860?p=KJ0C2yDSIj805S4gJU|MS Teams]]
+  * Recording:  TDA
+  * Presentation slides:  TDA
-  * **[INTRO] 2026.10.08**: Grzegorz J. Nalepa,  professor @ Jagiellonian University, [[--]]
-    * Meeting link: TDA
+* **[INTRO] 2026.10.08**: Grzegorz J. Nalepa,  professor @ Jagiellonian University, [[--]]
-    * Recording:  -
+  * Meeting link: TDA
-    * Presentation slides:  -
+  * Recording:  -
+  * Presentation slides:  -
 ===== Schedule Spring 2026 =====
@@ Line 588: / Line 593: @@
+==== 2026-10-15 ====
+<WRAP column 15%>
+{{ :aira:enrique-valero-foto.jpg?200| }}
+</WRAP>
+<WRAP column 75%>
+**Speaker**: Enrique Valero,  PhD Candidate @ Technical University of Madrid
+**Title**: Group counterfactual explanations: State-of-the-art and future research
+**Abstract**:
+Existing methods for group counterfactual explanations often fail to generalize, rely on strict assumptions, or distort group geometry. I explore how to overcome this by learning an optimal transport map that efficiently generates geometry-preserving counterfactuals for any instance without re-optimization, outperforming current baselines across both linear and non-linear models. I also provide insight on future lines of research and applications of (group) counterfactual explanations with respect to the broader state-of-the-art, such as LLMs or industrial applications.
+**Biogram**:
+Enrique Valero Leal is a final-year ELLIS PhD student at both the Technical University of Madrid and Ludwig-Maximilians University of Munich. His research focuses on interpretable machine learning,  probabilistic models, and causality, with technical experience in Industry 4.0 applications.
+</WRAP>
+<WRAP clear></WRAP>
 ==== 2026-06-18 ====